A Novel Intrusion Detection System based on Extreme Machine Learning and Multi-Voting Technology
Jianlei Gao, Senchun Chai, Chen Zhang, Baihai Zhang, Lingguo Cui · 2019
With the fast development of networking technology, billions of devices have been developed with network function. When the scale of a network traffic grows by an order of magnitude, traditional intrusion detection system (IDS) are no longer effective to detect malicious network intrusions. In our work, we propose a novel network intrusion detection framework based on extreme learning machine (ELM) and multi-voting technology (MVT). Due to the real time feature of ELM, several independent ELM networks can be trained simultaneously. The final results are obtained by MVT strategy. The standard UNSW-NB15 data set has been used to evaluate the performance of the proposed method. The experimental result illustrated that the high accuracy can be achieved by using the proposed method.